# Santiago explains how PAN 2 lets agents simulate actions before choosing

> Original title: This is a pretty cool idea:

- Source: Santiago
- Published: 2026-11-10T19:10:23.000Z
- Bad Influence: https://badinfluence.news/items/apy244z3v22dd1h1r3vxg633r
- Original: https://x.com/svpino/status/2120232621053788454

## Summary

Santiago explains that PAN 2, a world model from the Institute of Foundation Models, lets an agent simulate each possible action and pick the best outcome. He describes its Generative Latent Prediction design, with an LLM handling conceptual reasoning and a 29B LDM rendering the predicted scene. He says the weights, training code, and inference code are released under Apache 2.0.

## Post

This is a pretty cool idea:

Let your agent simulate each potential action before picking the best one.

The model is PAN 2, a world model from the Institute of Foundation Models (IFM). They call this "simulative reasoning".

The attached video shows an example with a surfer: same wave, three different moments to pop up. PAN 2 plays out all three, and only one of them catches the wave, so that’s the one he goes with.

The model uses Generative Latent Prediction (GLP), and here is how it works:

• In: the current scene plus an action, with how long to simulate

• Out: what happens next, as a video you can check

There are two reasoning parts:

1. Conceptual reasoning: The LLM is the backbone here. It reasons about what happens next.

2. Perceptual reasoning: A 29B LDM fills in what it looks like.

This is all open under Apache 2.0!

They provided the weights, training code, and inference code, so you can run it and build on it yourself.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2120232526459662336%2Fimg%2FFvTG8HYRognxCam8.jpg&mode=thumb&exp=1794528000&sig=8d3ab3df66513903)